Type | Workflows |
Stats | 1,975 |
Reviews | (158) |
Published | May 10, 2024 |
Base Model | |
Hash | AutoV2 34CB0F2006 |
Abominable Spaghetti Workflow
The unmatched prompt adherence of PixArt Sigma plus the perfect attention to detail of the SD 1.5 models, all in one ready-to-use workflow for ComfyUI.
Required Nodes
To use this workflow, you'll need to have ComfyUI_ExtraModels installed. Here's how to do it on Linux in four simple steps:
cd <your-comfyui-directory>
cd custom_nodes
git clone https://github.com/city96/ComfyUI_ExtraModels
pip install -r requirements.txt
Note 1: Running pip may require activating the virtual environment used to run ComfyUI.
Note 2: Windows users can refer to the installation methods suggested on the project GitHub Page.
Note 3: ComfyUI_ExtraModels has various dependencies and requirements on which it heavily relies. Therefore, it might be more convenient to install it using a node manager like ComfyUI Manager.
Required Files
You also need to have the following 6 files locally:
From PixArt Sigma GitHub Page:
PixArt-Sigma-XL-2-1024-MS.pth
From PixArt Text Encoder Hugging Face Repo:
config.json
model.safetensors.index.json
model-00001-of-00002.safetensors
model-00002-of-00002.safetensors
From PixArt VAE Hugging Face Repo:
diffusion_pytorch_model.safetensors
Rename the file 'diffusion_pytorch_model.safetensors' to 'pixart_sigma_vae.safetensors'
Once obtained, place the files within the ComfyUI directory as outlined below:
comfyui / models / checkpoints
PixArt-Sigma-XL-2-1024-MS.pth
Photon_v1.safetensor (or any other SD15 model)
comfyui / models / t5
config.json
model.safetensors.index.json
model-00001-of-00002.safetensors
model-00002-of-00002.safetensors
comfyui / models / vae
pixart_sigma_vae.safetensors
Version History
v2
- Simplified steps configuration.
- Added nodes to easily modify CFG and SEED parameters.
- Aesthetic node color/position changes for better usability.
- Updated install instructions with corrections and clarity.
- Improved final image organization into date-based folders.
v1
- The initial release providing core functionality.